OpenAI Privacy Filter

Released
2026-04-22
Last refreshed
2026-04-23
Status
Researched 180d ago
Open sourceCommercial use: permittedLong contextClassification

OpenAI Privacy Filter is a released long context and classification model with open-source and 128K context; evaluate it while provider pricing coverage matures.

OpenAI releases · 45 in the last 12 months · this family litChangelog →
Specifications
Released
2026-04-22
Context
128K
Parameters
1.5B
Architecture
Encoder Only
Specialization
safety
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Pretrained
Created by
OpenAI

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing

No tracked provider pricing is available yet.

Links
Website HuggingFace

About

OpenAI Privacy Filter is an Apache 2.0 open-weight bidirectional token-classification model for detecting and redacting personally identifiable information in text. OpenAI reports 1.5B total parameters, 50M active parameters, 128k-token context, and availability on Hugging Face and GitHub; this is a new specialist model release rather than a ChatGPT feature or endpoint alias.

Providers

No active provider routes are tracked for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Long context

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.